Metraipolis › archive › dc_0163bc0c280c

Which papyrus HTR is good enough? Character-error-rate tolerance of four papyrological tasks on Greek texts — arXiv:2609.37755

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.37755
License (as archived)
CC0-1.0
Archived
2026-10-07T16:57:07.556Z
SHA-256 of the archived text
a5f21ada0889480985e93da7070719fa1c5b7b2c1e57f6008d276a6b1000cfab
Stable URL of this page
https://metraipolis.com/documento/dc_0163bc0c280c

How to cite

Which papyrus HTR is good enough? Character-error-rate tolerance of four papyrological tasks on Greek texts — arXiv:2609.37755 — arXiv (en), https://arxiv.org/abs/2609.37755 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0163bc0c280c (Metraipolis archive dc_0163bc0c280c, sha256 a5f21ada0889480985e93da7070719fa1c5b7b2c1e57f6008d276a6b1000cfab)
BibTeX
@misc{dc0163bc0c280c,
  title = {Which papyrus HTR is good enough? Character-error-rate tolerance of four papyrological tasks on Greek texts — arXiv:2609.37755},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.37755},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0163bc0c280c; sha256 a5f21ada0889480985e93da7070719fa1c5b7b2c1e57f6008d276a6b1000cfab},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.37755. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Purpose: Most Greek papyri remain unpublished and undigitised; a handwritten text recognition (HTR) pipeline that transcribes them automatically would let scholars discover documents and literary works that have so far gone unread. Recognition systems for Ancient Greek papyri are in statu nascendi, and how accurate they must be for a given papyrological task has not been examined. To answer this and set a benchmark for Greek papyrus HTR, we test a range of character error rates (CER) against four papyrological tasks, using published editions as ground truth. Methods: From 63,846 current editions of Greek texts in this http URL , we imitate a letters-only "perfect HTR" output by removing the editorial layer, then degrade it with a seeded algorithm to exact CERs of 1 - 50%, with lost lines and four error-shape variants. On these data we train small models (TF-IDF, fastText, a character CNN, ByT5-small) for document type, dating and documentary-versus-literary classification, and apply eight keyword search methods. We compare models trained on clean text with models retrained at a specific CER level, and evaluate across CERs. Results: Tolerance differs by task. With clean-trained models, documentary-versus-literary classification retains 90% of its metric up to 20% CER; document type up to 7.5%; subtypes and search up to 5%; dating only up to 3%. Retraining on text containing character errors largely eliminates the sharp degradation that otherwise sets in above 15% CER. Models generally tolerate concentrated damage in a long document better than small errors spread across a short text. Conclusion: The study provides a CER target for each of the four tasks and shows that models trained on noisy text make current, imperfect text recognition useful for them.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2609.37755 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T16:27:03.331Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).